Topic models for translation quality estimation for gisting purposes
作者： Lucia Specia , Raphael Rubino , Jennifer Foster , Jose de Souza
DOI:
关键词:
摘要: This paper addresses the problem of predicting how adequate a machine translation is for gisting purposes. It focuses on contribution lexicalised features based different types topic models, as we believe these are more robust than those used in previous work, which depend linguistic processors that often unreliable automatic translations. Experiments with number datasets show promising results: use models outperforms state-of-the-art approaches by large margin all annotated adequacy.
qt21.eu 参考文章(22)
Nicola Bertoldi, Marcello Federico, Mauro Cettolo, IRSTLM: an open source toolkit for handling large scale language models. conference of the international speech communication association. pp. 1618- 1621 ,(2008)
Yashar Mehdad, Marcello Federico, Matteo Negri, Match without a Referee: Evaluating MT Adequacy without Reference Translations workshop on statistical machine translation. pp. 171- 180 ,(2012)
Fred Hollowood, Raphael Rubino, Rasul Samad Zadeh Kaljahi, Jennifer Foster, Joachim Wagner, Johann Roturier, DCU-Symantec Submission for the WMT 2012 Quality Estimation Task workshop on statistical machine translation. pp. 138- 144 ,(2012)
Sandy Lovie, Shannon, Claude E Encyclopedia of Statistics in Behavioral Science. ,(2005) , 10.1002/0470013192.BSA610
David M Blei, Andrew Y Ng, Michael I Jordan, None, Latent dirichlet allocation Journal of Machine Learning Research. ,vol. 3, pp. 993- 1022 ,(2003) , 10.5555/944919.944937
S. Kullback, R. A. Leibler, On Information and Sufficiency Annals of Mathematical Statistics. ,vol. 22, pp. 79- 86 ,(1951) , 10.1214/AOMS/1177729694
Lucia Specia, Dhwaj Raj, Marco Turchi, Machine translation evaluation versus quality estimation Machine Translation. ,vol. 24, pp. 39- 50 ,(2010) , 10.1007/S10590-010-9077-2
David Mimno, Hanna M. Wallach, Jason Naradowsky, David A. Smith, Andrew McCallum, Polylingual Topic Models empirical methods in natural language processing. pp. 880- 889 ,(2009) , 10.3115/1699571.1699627
George Doddington, Automatic evaluation of machine translation quality using n-gram co-occurrence statistics international conference on human language technology research. pp. 138- 145 ,(2002) , 10.3115/1289189.1289273
Lucia Specia, Chris Callison-Burch, Christof Monz, Matt Post, Radu Soricut, Philipp Koehn, Findings of the 2012 Workshop on Statistical Machine Translation workshop on statistical machine translation. pp. 10- 51 ,(2012)